Weather state pattern recognition modeling method and device based on irradiance

Abstract

The invention relates to the technical field of photovoltaic power prediction, and discloses an irradiance-based weather state pattern recognition modeling method and device, and the method comprises the steps: obtaining irradiance data and a weather type in a preset time period; the irradiance data comprises earth surface irradiance data and corresponding extraterrestrial irradiance theoretical value data; performing feature extraction on the earth surface irradiance data and the extraterrestrial irradiance theoretical value data to obtain feature parameters; based on the characteristic parameters and the weather types, training to obtain a weather state pattern recognition model; the weather state mode recognition model is used for classifying the new irradiance data and determining a corresponding weather type. According to the technical scheme provided by one or more embodiments of the invention, the irradiance characteristic parameters and the weather types are used to achieve the effect of establishing the accurate weather state pattern recognition model.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power prediction, and in particular to a weather state pattern recognition modeling method and device based on irradiance. Background Art

[0002] Weather state pattern recognition classification modeling method, based on the in-depth understanding of the changes in solar radiation under the influence of atmospheric movement, has become a key technology for photovoltaic power station power generation prediction. In related technologies, atmospheric movement determines the weather state, and the weather state determines the changes in solar radiation, resulting in obvious differences in the mapping relationship between the input / output of the prediction model under different weather conditions. However, in classification modeling, only historical operating data with complete weather type information can be used for model learning and training. For most historical data, the records already contain the weather type information corresponding to that day, but in practice, the corresponding weather type information of historical data is often missing due to some reasons, such as communication failures, service interruptions, storage errors, etc. Historical data with missing weather type information cannot be used for classification modeling learning and training, which destroys the integrity of the training data and may lead to reduced performance of the prediction model or even difficulty in modeling.

[0003] The relationship between the surface solar irradiance and the extraterrestrial solar irradiance is closely related to the change of weather conditions. According to meteorological theory and the results of statistical analysis of a large amount of actual data, if the change of weather conditions in a certain place within a specified time range is very small, then the change law of its surface solar irradiance is very close to the change law of extraterrestrial solar irradiance. However, the solar radiation received by the surface is affected by factors such as longitude, latitude, altitude, season, climate, environment, and air quality, and there are large differences. The surface solar irradiance has both basic evolution laws and obvious intermittent characteristics, and at the same time has significant characteristics of complex and random changes. By comparing and analyzing the differences in the change laws of surface and extraterrestrial solar irradiance, we can more accurately grasp the basic situation of weather state changes within the corresponding time range.

[0004] In view of this, a method for establishing a weather state pattern recognition model is needed to accurately identify the weather type based on irradiance data. Summary of the invention

[0005] In view of this, the present invention provides a weather state pattern recognition modeling method and device based on irradiance to solve the problem of lack of accurate weather state pattern recognition model.

[0006] In the first aspect, the present invention provides a weather condition pattern recognition modeling method based on irradiance, the method comprising: obtaining irradiance data and weather type within a preset time period; the irradiance data comprises surface irradiance data and corresponding extraterrestrial irradiance theoretical value data; performing feature extraction on the surface irradiance data and the extraterrestrial irradiance theoretical value data to obtain feature parameters; based on the feature parameters and weather type, training to obtain a weather condition pattern recognition model; the weather condition pattern recognition model is used to classify new irradiance data and determine the corresponding weather type.

[0007] In the second aspect, the present invention provides a weather condition pattern recognition modeling device based on irradiance, the device comprising: a data acquisition module, used to obtain irradiance data and weather type within a preset time period; the irradiance data comprises surface irradiance data and corresponding extraterrestrial irradiance theoretical value data; a feature extraction module, used to perform feature extraction on surface irradiance data and extraterrestrial irradiance theoretical value data to obtain feature parameters; a model training module, used to train a weather condition pattern recognition model based on the feature parameters and weather type; the weather condition pattern recognition model is used to classify new irradiance data and determine the corresponding weather type.

[0008] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the irradiance-based weather state pattern recognition and modeling method of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0009] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the irradiance-based weather state pattern recognition and modeling method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0010] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the irradiance-based weather state pattern recognition modeling method of the first aspect or any corresponding embodiment thereof.

[0011] The technical solution provided by one or more embodiments of the present invention obtains irradiance data and corresponding weather types within a preset time period, wherein the irradiance data consists of surface irradiance data and its corresponding extraterrestrial irradiance theoretical value data, and feature extraction is performed on the surface irradiance data and the extraterrestrial irradiance theoretical value data to obtain key feature parameters. Using these extracted feature parameters and known weather types, a weather state pattern recognition model with accurate weather recognition capabilities is trained and constructed, and the model can classify new irradiance data to identify and determine its corresponding weather type. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 is a flow chart of a weather state pattern recognition modeling method based on irradiance according to an embodiment of the present invention;

[0014] Figure 2 is a structural block diagram of a weather state pattern recognition and modeling device based on irradiance according to an embodiment of the present invention;

[0015] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] The embodiment of the present invention provides a weather state pattern recognition modeling method based on irradiance, which achieves the effect of establishing an accurate weather state pattern recognition model by using irradiance characteristic parameters and weather types.

[0018] According to an embodiment of the present invention, an embodiment of a weather state pattern recognition modeling method based on irradiance is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0019] In this embodiment, a weather state pattern recognition modeling method based on irradiance is provided. Figure 1 is a flow chart of a weather state pattern recognition modeling method based on irradiance according to an embodiment of the present invention, such as Figure 1 As shown, the process includes the following steps:

[0020] Step S101, obtaining irradiance data and weather type within a preset time period; the irradiance data includes surface irradiance data and corresponding extraterrestrial irradiance theoretical value data.

[0021] Weather type is a way to classify the state of the atmosphere. It divides the weather into different categories based on various meteorological factors in the atmosphere. Each weather type represents a specific set of meteorological conditions, which usually remain relatively stable over a certain period of time. Taking into account the representativeness of typical weather types and the similarity between other weather types and these typical weather types, the weather types can be summarized and merged according to the degree of similarity. Each subset contains more than one weather type, and these subsets are called generalized weather types. For photovoltaic power stations in different locations, the changes in weather conditions and the distribution of weather types are different. Therefore, the number of generalized weather types can be adjusted according to actual conditions. In other words, for places where the weather state changes are relatively simple, the number of corresponding generalized weather types can be appropriately reduced; conversely, the number of generalized weather types can be appropriately increased.

[0022] Step S102, extracting features from the surface irradiance data and the extraterrestrial irradiance theoretical value data to obtain feature parameters.

[0023] Surface irradiance data refers to the measurement of solar radiation energy actually measured on the surface of the earth, which is usually affected by factors such as clouds, terrain, and atmospheric conditions. Extraterrestrial irradiance theoretical value data refers to the standard measurement of solar radiation energy outside the earth's atmosphere, that is, theoretically without the influence of the atmosphere. This value is usually calculated based on astronomical algorithms. Feature extraction is a data processing process that aims to identify attributes or features from raw data that help understand data patterns and structures. In this process, statistical analysis, mathematical transformations, and other methods may be used. Feature parameters refer to parameters extracted from surface irradiance data and extraterrestrial irradiance theoretical value data that can represent certain characteristics of the data. These parameters may include the variance, maximum value, and rate of change of irradiance, which can reflect different aspects of weather conditions.

[0024] Through feature extraction, a set of numerical feature parameters can be obtained, which can quantify the key characteristics of surface and extraterrestrial irradiance data and provide a basis for pattern recognition and classification of weather conditions. These feature parameters can then be used to train weather state pattern recognition models to predict and classify weather conditions corresponding to new irradiance data.

[0025] Step S103, based on the characteristic parameters and the weather type, a weather state pattern recognition model is trained; the weather state pattern recognition model is used to classify the new irradiance data and determine the corresponding weather type.

[0026] The support vector machine method can be used to establish a weather state pattern recognition model based on irradiance characteristic parameters. New irradiance data refers to surface irradiance data that has not yet been classified. These data need to be determined by the model to determine their corresponding weather state. Ultimately, the model will assign a most likely weather type label to the new irradiance data, which is based on the relationship between the characteristic parameters and weather types learned by the model from the training data.

[0027] The irradiance-based weather condition pattern recognition modeling method provided in this embodiment extracts key characteristic parameters in the irradiance data. These parameters can significantly reflect the irradiance change characteristics under different weather conditions. After being used as the input of the weather condition pattern recognition model, a weather condition pattern recognition model with accurate weather recognition capabilities is established.

[0028] In some optional implementations, the characteristic parameters extracted in step 102 above include:

[0029] Step a11, calculate the clearness index K t , Sunny index K t It is based on the following formula:

[0030]

[0031] Where t represents the sampling time point within 24 hours, G s,i Represents the discrete sampling value of surface irradiance, N represents the number of sampling points within 24 hours, G 0,i Represents the theoretical calculated value of extraterrestrial irradiance corresponding to the surface irradiance.

[0032] The accumulation of irradiance over a period of time is called the exposure corresponding to that period. In order to measure the difference between the surface irradiance and the overall exposure of extraterrestrial irradiance, the ratio of the two is defined as the clearness index.

[0033] Step a12, calculate the maximum surface irradiance G s,max , the maximum surface irradiance G s,max It is based on the following formula:

[0034] G a,max =max{G s,i}

[0035] Among them, G s,i Represents the discrete sampling value of surface irradiance, i=1,....,N, N represents the number of sampling points within 24 hours.

[0036] The maximum value of surface irradiance during sunshine hours represents the intensity of solar radiation on that day to a certain extent.

[0037] Step a13, calculate the surface irradiance variance V g , surface irradiance variance V g It is based on the following formula:

[0038]

[0039] Among them, G s,i Represents the discrete sampling value of surface irradiance, and N represents the number of sampling points within 24 hours.

[0040] The variance of surface irradiance describes the degree of fluctuation of surface solar radiation.

[0041] Step a14, calculating the maximum value of the third-order derivative of the irradiance difference TODmax, which is used to describe the local variation characteristics of the surface irradiance and the extraterrestrial irradiance.

[0042] When the weather conditions change, the surface irradiance may suddenly change at any time, and the amplitude and frequency of the sudden change are also different, but the corresponding extraterrestrial irradiance is not affected by the weather conditions and still maintains its inherent change law. Therefore, the degree to which the surface irradiance deviates from the inherent change trend can be described by observing the difference between the surface irradiance and the extraterrestrial irradiance, thereby reflecting the change of weather conditions. In order to describe the random fluctuations of weather conditions, it is necessary to extract mathematical indicators that can characterize the local change characteristics of the irradiance difference. The derivative of the irradiance difference with respect to time should be able to reflect the local characteristics of its random changes and can be used as a potential candidate feature quantity. Considering that the third-order derivative of the irradiance difference is a discrete data sequence with a large number of dimensions, it is not appropriate to directly input all of its values ​​as feature parameters, which will make the dimension of the input space too high. Therefore, the maximum value of the third-order derivative of the irradiance difference is selected as the feature parameter.

[0043] Step a15, calculating the discrete difference LS1 and the normalized discrete difference LS2, the discrete difference LS1 and the normalized discrete difference LS2 are obtained based on the following formula:

[0044]

[0045] in, G s,i Represents the discrete sampled value of the surface irradiance, G 0,i It represents the theoretical calculated value of extraterrestrial irradiance corresponding to the surface irradiance, and N represents the number of sampling points within 24 hours.

[0046] The discrete difference reflects the difference in actual values ​​of surface and extraterrestrial irradiance, while the normalized discrete difference eliminates the influence of the difference in values ​​between the two and only reflects the difference in the shapes of the two curves.

[0047] Step a16, calculate the consistency coefficient K cc , consistency coefficient K cc It is based on the following formula:

[0048]

[0049] in, G s,i Represents the discrete sampled value of the surface irradiance, G 0,i It represents the theoretical calculated value of extraterrestrial irradiance corresponding to the surface irradiance, i=1,....,N, where N represents the number of sampling points within 24 hours.

[0050] When |G s,i -G s,i-1 |≠0, it means that the current surface irradiance value is not equal to the value at the previous moment, which means that the surface irradiance is changing. This can explain the trend of this change. If the irradiance value increases, if the irradiance value decreases, then

[0051] For extraterrestrial irradiance It also has the meaning of an indicator that reflects the increase or decrease of its value. It is defined as an indicator to determine whether the change trend of surface and extraterrestrial irradiance is consistent. (all values ​​are 1 or all values ​​are -1), then When the two trends are opposite, but

[0052] The consistency coefficient is the sum of the trend indicators of each sampling time period, which can be used as a measure of the consistency of the change trend of surface and extraterrestrial irradiance within a certain time range. The larger the consistency coefficient, the more consistent the change trends of the two, and vice versa. s,i -G s,i-1 |=0or|G 0,i -G 0,i-1 |=0), the trend indicator is zero, and this period of time has no effect on the size of the overall trend consistency coefficient.

[0053] The method for calculating characteristic parameters provided in this embodiment selects characteristic parameters that can reflect weather conditions to identify weather condition patterns. In the process of extracting irradiance characteristic parameters, the overall characteristics of the data series in a statistical sense, the difference discrete characteristics of the difference measurement between surface and extraterrestrial irradiance, and the change trend characteristics reflecting the similarities and differences in the evolution and development directions of extraterrestrial and surface irradiance are mainly considered.

[0054] In this embodiment, a weather state pattern recognition modeling device based on irradiance is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0055] This embodiment provides a weather state pattern recognition modeling device based on irradiance, such as Figure 2 As shown, including:

[0056] The data acquisition module 201 is used to acquire irradiance data and weather type within a preset time period; the irradiance data includes surface irradiance data and corresponding extraterrestrial irradiance theoretical value data.

[0057] The feature extraction module 202 is used to extract features from the surface irradiance data and the extraterrestrial irradiance theoretical value data to obtain feature parameters.

[0058] The model training module 203 is used to train and obtain a weather state pattern recognition model based on characteristic parameters and weather types; the weather state pattern recognition model is used to classify new irradiance data and determine the corresponding weather type.

[0059] In some optional implementations, the feature extraction module 202 includes:

[0060] The first feature extraction unit is used to calculate the clearness index K t , Sunny index K t It is based on the following formula:

[0061]

[0062] Where t represents the sampling time point within 24 hours, G s,i Represents the discrete sampling value of surface irradiance, N represents the number of sampling points within 24 hours, G 0,i Represents the theoretical calculated value of extraterrestrial irradiance corresponding to the surface irradiance.

[0063] The second feature extraction unit is used to calculate the maximum surface irradiance G s,max , the maximum surface irradiance G s,max It is based on the following formula:

[0064] G s,max =max{G s,i}

[0065] Among them, G s,i Represents the discrete sampling value of surface irradiance, i=1,....,N, N represents the number of sampling points within 24 hours.

[0066] The third feature extraction unit is used to calculate the surface irradiance variance V g , surface irradiance variance V g It is based on the following formula:

[0067]

[0068] Among them, G s,i Represents the discrete sampling value of surface irradiance, and N represents the number of sampling points within 24 hours.

[0069] The fourth feature extraction unit is used to calculate the maximum value of the third-order derivative of the irradiance difference TODmax, and the maximum value of the third-order derivative of the irradiance difference TODmax is used to describe the local change characteristics of the surface irradiance and the extraterrestrial irradiance.

[0070] The fifth feature extraction unit is used to calculate the discrete difference LS1 and the normalized discrete difference LS2, and the discrete difference LS1 and the normalized discrete difference LS2 are obtained based on the following formula:

[0071]

[0072]

[0073] in, G s,i Represents the discrete sampled value of the surface irradiance, G 0,i It represents the theoretical calculated value of extraterrestrial irradiance corresponding to the surface irradiance, and N represents the number of sampling points within 24 hours.

[0074] The sixth feature extraction unit is used to calculate the consistency coefficient K cc , consistency coefficient K cc It is based on the following formula:

[0075]

[0076] in, G s,i Represents the discrete sampled value of the surface irradiance, G 0,i It represents the theoretical calculated value of extraterrestrial irradiance corresponding to the surface irradiance, i=1,....,N, where N represents the number of sampling points within 24 hours.

[0077] In this embodiment, a weather condition pattern recognition modeling device based on irradiance is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0078] The embodiment of the present invention also provides a computer device having the above Figure 2 The irradiance-based weather state pattern recognition modeling device shown.

[0079] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 3As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0080] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0081] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0082] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0083] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0084] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0085] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0086] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0087] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0088] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A weather state pattern recognition modeling method based on irradiance, characterized in that: The method comprises: Acquire irradiance data and weather type within a preset time period; the irradiance data includes surface irradiance data and corresponding extraterrestrial irradiance theoretical value data; Extracting features from the surface irradiance data and the extraterrestrial irradiance theoretical value data to obtain feature parameters; Based on the characteristic parameters and the weather type, a weather state pattern recognition model is trained; the weather state pattern recognition model is used to classify new irradiance data and determine the corresponding weather type.

2. The method according to claim 1, characterized in that: The characteristic parameters include the clearness index K t , the clearness index K t It is based on the following formula: Where t represents the sampling time point within 24 hours, G s,i represents the discrete sampling value of the surface irradiance, N represents the number of sampling points within 24 hours, G 0,i Represents the theoretical calculated value of the extraterrestrial irradiance corresponding to the surface irradiance.

3. The method according to claim 1, characterized in that The characteristic parameters include the maximum surface irradiance G s,max , the maximum surface irradiance G s,max It is based on the following formula: G s，max =max{G s，i } Among them, G s,i Represents the discrete sampling value of the surface irradiance, i=1,....,N, N represents the number of sampling points within 24 hours.

4. The method according to claim 1, characterized in that: The characteristic parameters include the surface irradiance variance V g , the surface irradiance variance V g It is based on the following formula: Among them, G s,i represents the discrete sampling value of the surface irradiance, and N represents the number of sampling points within 24 hours.

5. The method according to claim 1, characterized in that The characteristic parameters also include the maximum value of the third-order derivative of the irradiance difference TODmax, and the maximum value of the third-order derivative of the irradiance difference TODmax is used to describe the local variation characteristics of the surface irradiance and the extraterrestrial irradiance.

6. The method according to claim 1, characterized in that The characteristic parameters also include a discrete difference LS1 and a normalized discrete difference LS2, and the discrete difference and the normalized discrete difference are obtained based on the following formula: in, G s,i represents the discrete sampled value of the surface irradiance, G 0,i represents the theoretical calculated value of the extraterrestrial irradiance corresponding to the surface irradiance, and N represents the number of sampling points within 24 hours.

7. The method according to claim 1, characterized in that The characteristic parameters also include the consistency coefficient K cc , the consistency coefficient K cc It is based on the following formula: in, G s,i represents the discrete sampled value of the surface irradiance, G 0,i represents the theoretical calculated value of the extraterrestrial irradiance corresponding to the surface irradiance, i=1,....,N, N represents the number of sampling points within 24 hours.

8. A weather state pattern recognition modeling device based on irradiance, characterized in that: The device comprises: A data acquisition module is used to acquire irradiance data and weather type within a preset time period; the irradiance data includes surface irradiance data and corresponding extraterrestrial irradiance theoretical value data; A feature extraction module is used to extract features from the surface irradiance data and the extraterrestrial irradiance theoretical value data to obtain feature parameters; The model training module is used to train a weather state pattern recognition model based on the characteristic parameters and the weather type; the weather state pattern recognition model is used to classify new irradiance data and determine the corresponding weather type.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images